mirror of
https://github.com/wshobson/agents.git
synced 2026-03-18 09:37:15 +00:00
3802bca865
Plugin Scope Improvements: - Remove language-specialists plugin (not task-focused) - Split specialized-domains into 5 focused plugins: * blockchain-web3 - Smart contract development only * quantitative-trading - Financial modeling and trading only * payment-processing - Payment gateway integration only * game-development - Unity and Minecraft only * accessibility-compliance - WCAG auditing only - Split business-operations into 3 focused plugins: * business-analytics - Metrics and reporting only * hr-legal-compliance - HR and legal docs only * customer-sales-automation - Support and sales workflows only - Fix infrastructure-devops scope: * Remove database concerns (db-migrate, database-admin) * Remove observability concerns (observability-engineer) * Move slo-implement to incident-response * Focus purely on container orchestration (K8s, Docker, Terraform) - Fix customer-sales-automation scope: * Remove content-marketer (unrelated to customer/sales workflows) Marketplace Statistics: - Total plugins: 27 (was 22) - Tool coverage: 100% (42/42 tools referenced) - Fat plugins removed: 3 (language-specialists, specialized-domains, business-operations) - All plugins now have clear, focused tasks Model Migration: - Migrate all 42 tools from claude-sonnet-4-0/opus-4-1 to model: sonnet - Migrate all 15 workflows from claude-opus-4-1 to model: sonnet - Use short model syntax consistent with agent files Documentation Updates: - Update README.md with refined plugin structure - Update plugin descriptions to be task-focused - Remove anthropomorphic and marketing language - Improve category organization (now 16 distinct categories) Ready for October 9, 2025 @ 9am PST launch
3.1 KiB
3.1 KiB
model
| model |
|---|
| sonnet |
Implement a full-stack feature across multiple platforms with coordinated agent orchestration:
[Extended thinking: This workflow orchestrates a comprehensive feature implementation across backend, frontend, mobile, and API layers. Each agent builds upon the work of previous agents to create a cohesive multi-platform solution.]
Phase 1: Architecture and API Design
1. Backend Architecture
- Use Task tool with subagent_type="backend-architect"
- Prompt: "Design backend architecture for: $ARGUMENTS. Include service boundaries, data models, and technology recommendations."
- Output: Service architecture, database schema, API structure
2. GraphQL API Design (if applicable)
- Use Task tool with subagent_type="graphql-architect"
- Prompt: "Design GraphQL schema and resolvers for: $ARGUMENTS. Build on the backend architecture from previous step. Include types, queries, mutations, and subscriptions."
- Output: GraphQL schema, resolver structure, federation strategy
Phase 2: Implementation
3. Frontend Development
- Use Task tool with subagent_type="frontend-developer"
- Prompt: "Implement web frontend for: $ARGUMENTS. Use the API design from previous steps. Include responsive UI, state management, and API integration."
- Output: React/Vue/Angular components, state management, API client
4. Mobile Development
- Use Task tool with subagent_type="mobile-developer"
- Prompt: "Implement mobile app features for: $ARGUMENTS. Ensure consistency with web frontend and use the same API. Include offline support and native integrations."
- Output: React Native/Flutter implementation, offline sync, push notifications
Phase 3: Quality Assurance
5. Comprehensive Testing
- Use Task tool with subagent_type="test-automator"
- Prompt: "Create test suites for: $ARGUMENTS. Cover backend APIs, frontend components, mobile app features, and integration tests across all platforms."
- Output: Unit tests, integration tests, e2e tests, test documentation
6. Security Review
- Use Task tool with subagent_type="security-auditor"
- Prompt: "Audit security across all implementations for: $ARGUMENTS. Check API security, frontend vulnerabilities, and mobile app security."
- Output: Security report, remediation steps
Phase 4: Optimization and Deployment
7. Performance Optimization
- Use Task tool with subagent_type="performance-engineer"
- Prompt: "Optimize performance across all platforms for: $ARGUMENTS. Focus on API response times, frontend bundle size, and mobile app performance."
- Output: Performance improvements, caching strategies, optimization report
8. Deployment Preparation
- Use Task tool with subagent_type="deployment-engineer"
- Prompt: "Prepare deployment for all components of: $ARGUMENTS. Include CI/CD pipelines, containerization, and monitoring setup."
- Output: Deployment configurations, monitoring setup, rollout strategy
Coordination Notes
- Each agent receives outputs from previous agents
- Maintain consistency across all platforms
- Ensure API contracts are honored by all clients
- Document integration points between components
Feature to implement: $ARGUMENTS